{"id":"https://openalex.org/W1970684977","doi":"https://doi.org/10.1142/s0219720010004847","title":"GENETACK: FRAMESHIFT IDENTIFICATION IN PROTEIN-CODING SEQUENCES BY THE VITERBI ALGORITHM","display_name":"GENETACK: FRAMESHIFT IDENTIFICATION IN PROTEIN-CODING SEQUENCES BY THE VITERBI ALGORITHM","publication_year":2010,"publication_date":"2010-03-24","ids":{"openalex":"https://openalex.org/W1970684977","doi":"https://doi.org/10.1142/s0219720010004847","mag":"1970684977","pmid":"https://pubmed.ncbi.nlm.nih.gov/20556861"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720010004847","is_oa":true,"landing_page_url":"https://doi.org/10.1142/s0219720010004847","pdf_url":"https://www.worldscientific.com/doi/pdf/10.1142/S0219720010004847","source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.worldscientific.com/doi/pdf/10.1142/S0219720010004847","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007556625","display_name":"Ivan Antonov","orcid":"https://orcid.org/0000-0002-8330-6907"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"IVAN ANTONOV","raw_affiliation_strings":["Division of Computational Science and Engineering, Georgia Institute of Technology, 801 Atlantic Drive, Atlanta, Georgia, USA 30332-0280, USA"],"affiliations":[{"raw_affiliation_string":"Division of Computational Science and Engineering, Georgia Institute of Technology, 801 Atlantic Drive, Atlanta, Georgia, USA 30332-0280, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057317686","display_name":"Mark Borodovsky","orcid":"https://orcid.org/0000-0002-1401-4046"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"MARK BORODOVSKY","raw_affiliation_strings":["Department of Biomedical Engineering and Division of Computational Science and Engineering, Georgia Institute of Technology, 313 Ferst Drive, Atlanta, Georgia, USA 30332-0535, USA"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering and Division of Computational Science and Engineering, Georgia Institute of Technology, 313 Ferst Drive, Atlanta, Georgia, USA 30332-0535, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007556625"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":2.5113,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.889376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"08","issue":"03","first_page":"535","last_page":"551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/frameshift-mutation","display_name":"Frameshift mutation","score":0.8899011015892029},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.6315152645111084},{"id":"https://openalex.org/keywords/orfs","display_name":"ORFS","score":0.615426242351532},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.5749346017837524},{"id":"https://openalex.org/keywords/gene-prediction","display_name":"Gene prediction","score":0.47812619805336},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.47504663467407227},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4705546200275421},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.47017377614974976},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.45987170934677124},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.45179036259651184},{"id":"https://openalex.org/keywords/coding-region","display_name":"Coding region","score":0.423096239566803},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39682736992836},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3930369019508362},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.23609870672225952},{"id":"https://openalex.org/keywords/open-reading-frame","display_name":"Open reading frame","score":0.17094489932060242},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.15494069457054138},{"id":"https://openalex.org/keywords/exon","display_name":"Exon","score":0.15117719769477844}],"concepts":[{"id":"https://openalex.org/C29906990","wikidata":"https://www.wikidata.org/wiki/Q1440688","display_name":"Frameshift mutation","level":4,"score":0.8899011015892029},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.6315152645111084},{"id":"https://openalex.org/C2780530800","wikidata":"https://www.wikidata.org/wiki/Q7072921","display_name":"ORFS","level":5,"score":0.615426242351532},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.5749346017837524},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.47812619805336},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.47504663467407227},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4705546200275421},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.47017377614974976},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.45987170934677124},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.45179036259651184},{"id":"https://openalex.org/C91779695","wikidata":"https://www.wikidata.org/wiki/Q3780824","display_name":"Coding region","level":3,"score":0.423096239566803},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39682736992836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3930369019508362},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.23609870672225952},{"id":"https://openalex.org/C47289529","wikidata":"https://www.wikidata.org/wiki/Q908550","display_name":"Open reading frame","level":4,"score":0.17094489932060242},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.15494069457054138},{"id":"https://openalex.org/C36823959","wikidata":"https://www.wikidata.org/wiki/Q373027","display_name":"Exon","level":3,"score":0.15117719769477844}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016368","descriptor_name":"Frameshift Mutation","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016368","descriptor_name":"Frameshift Mutation","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016368","descriptor_name":"Frameshift Mutation","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219720010004847","is_oa":true,"landing_page_url":"https://doi.org/10.1142/s0219720010004847","pdf_url":"https://www.worldscientific.com/doi/pdf/10.1142/S0219720010004847","source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},{"id":"pmid:20556861","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20556861","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of bioinformatics and computational biology","raw_type":null}],"best_oa_location":{"id":"doi:10.1142/s0219720010004847","is_oa":true,"landing_page_url":"https://doi.org/10.1142/s0219720010004847","pdf_url":"https://www.worldscientific.com/doi/pdf/10.1142/S0219720010004847","source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6399999856948853}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309321","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1970684977.pdf","grobid_xml":"https://content.openalex.org/works/W1970684977.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1873623553","https://openalex.org/W1976522966","https://openalex.org/W1977415113","https://openalex.org/W1983538916","https://openalex.org/W1990601349","https://openalex.org/W2004652640","https://openalex.org/W2009570821","https://openalex.org/W2039680623","https://openalex.org/W2056145855","https://openalex.org/W2086199046","https://openalex.org/W2088918459","https://openalex.org/W2105484013","https://openalex.org/W2106073189","https://openalex.org/W2106090237","https://openalex.org/W2110182011","https://openalex.org/W2129795133","https://openalex.org/W2134529224","https://openalex.org/W2137382844","https://openalex.org/W2143235667","https://openalex.org/W2154729337","https://openalex.org/W2158808847","https://openalex.org/W2160053034","https://openalex.org/W2164930421","https://openalex.org/W2396631988","https://openalex.org/W4245668478"],"related_works":["https://openalex.org/W2357819035","https://openalex.org/W2071205060","https://openalex.org/W2091106247","https://openalex.org/W2000357831","https://openalex.org/W2132439664","https://openalex.org/W2058497199","https://openalex.org/W1548013229","https://openalex.org/W2061235822","https://openalex.org/W1969028360","https://openalex.org/W2000136426"],"abstract_inverted_index":{"We":[0,113,137],"describe":[1],"a":[2,31,34,54,105,111,157],"new":[3],"program":[4,52,98,108,186],"for":[5],"ab":[6],"initio":[7],"frameshift":[8,142],"detection":[9],"in":[10,26,147],"protein-coding":[11,65,84],"nucleotide":[12],"sequences.":[13],"The":[14,50,67],"task":[15],"is":[16,177,205],"to":[17,30,89,94,192],"distinguish":[18],"the":[19,27,38,71,97,140,161,172,181,184],"same":[20,39],"strand":[21,40],"overlapping":[22,41,46],"ORFs":[23,42],"that":[24,43,75,86,139,171,187],"occur":[25],"sequence":[28,61],"due":[29,93],"presence":[32],"of":[33,59,145,149,163,175,183],"frameshifted":[35,64],"gene":[36],"from":[37],"encompass":[44],"true":[45,78],"or":[47],"adjacent":[48,79,83],"genes.":[49,136],"GeneTack":[51,115,176,198,204],"uses":[53,188],"hidden":[55],"Markov":[56],"model":[57],"(HMM)":[58],"genomic":[60],"with":[62,130,180],"possibly":[63],"regions.":[66],"Viterbi":[68],"algorithm":[69],"finds":[70],"maximum":[72],"likelihood":[73],"path":[74],"discriminates":[76],"between":[77],"genes":[80],"and":[81,124],"those":[82],"regions":[85],"just":[87],"appear":[88],"be":[90],"separate":[91],"entities":[92],"frameshifts.":[95],"Therefore,":[96],"can":[99],"identify":[100],"spurious":[101],"predictions":[102],"made":[103],"by":[104,110,156],"conventional":[106],"gene-finding":[107],"misled":[109],"frameshift.":[112],"tested":[114],"as":[116,118],"well":[117],"two":[119,164],"earlier":[120],"developed":[121],"programs":[122],"FrameD":[123],"FSFind":[125],"on":[126],"17":[127],"prokaryotic":[128],"genomes":[129],"frameshifts":[131],"introduced":[132],"randomly":[133],"into":[134],"known":[135],"observed":[138,170],"average":[141,173],"prediction":[143],"accuracy":[144,162,174,182],"GeneTack,":[146],"terms":[148],"(Sn":[150],"+":[151],"Sp)/2":[152],"values,":[153],"was":[154],"higher":[155],"significant":[158],"margin":[159],"than":[160],"other":[165],"programs.":[166],"In":[167],"addition,":[168],"we":[169],"favorably":[178],"compared":[179],"FSFind-BLAST":[185],"protein":[189],"database":[190],"search":[191],"verify":[193],"predicted":[194],"frameshifts,":[195],"even":[196],"though":[197],"does":[199],"not":[200],"use":[201],"external":[202],"evidence.":[203],"freely":[206],"available":[207],"at":[208],"http://topaz.gatech.edu/GeneTack/.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}